Survey of Hallucination in Natural Language Generation
Open accessThe DOI matches its Crossref record; 355 of the 360 references it cites were found in a registry or an index, and 4 are not checked yet; 224 of the 256 sources its claims cite were checked for support.
Abstract
Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation, and data-to-text generation. However, it is also apparent that deep learning based generation is prone to hallucinate unintended text, which degrades the system performance and fails to meet user expectations in many real-world scenarios. To address this issue, many studies have been presented in measuring and mitigating hallucinated texts, but these have never been reviewed in a comprehensive manner before. In this survey, we thus provide a broad overview of the research progress and challenges in the hallucination problem in NLG. The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions, and (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, and machine translation. This survey serves to facilitate collaborative efforts among researchers in tackling the challenge of hallucinated texts in NLG.
Verified 2026-11-19 · 4 references not checked yet
Overview
CoChat Summary
TL;DR
This survey provides a broad overview of hallucination in natural language generation, covering definitions, contributors, metrics, mitigation methods, and task-specific progress across summarization, dialogue, GQA, data-to-text, machine translation, vision-language generation, and LLMs. It distinguishes intrinsic from extrinsic hallucination and argues that hallucination must be treated differently across tasks and sources.
Key findings
- The survey categorizes hallucination into intrinsic hallucination, where generated output contradicts the source, and extrinsic hallucination, where output cannot be verified from the source; extrinsic hallucination is not always erroneous because it may come from factually correct external information.
- It reports prevalence examples from cited work: 25% of summaries generated by state-of-the-art abstractive summarization systems have hallucinated content; 62% of first sentences in WIKIBIO have additional information not stated in the corresponding infobox; and 74% of samples in the QMSum dataset consist of inconsistent facts.
- It reviews hallucination metrics as statistical, model-based (IE-based, QA-based, NLI-based, faithfulness classification, LM-based), and human evaluation, and mitigation methods as data-related and modeling/inference methods including architecture changes, planning/sketching, RL, multi-task learning, controllable generation, and post-processing.
- For LLMs, it notes that RLHF reduced the hallucination rate from 41% to 21% in closed-domain tasks for InstructGPT, and discusses reference-dependent and reference-free hallucination metrics plus mitigation via data refinement, RAG, safety fine-tuning, model editing, decoding methods, chain-of-thought variants, post-processing, and ensembling.
Methods
- Literature survey design: the paper reviews existing research on hallucination in NLG rather than conducting new experiments or primary data collection.
- Coverage: general NLG hallucination topics (definitions, contributors, metrics, mitigation, future directions) plus task-specific sections on abstractive summarization, dialogue generation, generative question answering, data-to-text generation, neural machine translation, vision-language generation, and large language models.
- Analysis: synthesizes and compares definitions, metrics, mitigation approaches, and future directions across tasks, with examples in tables and figures; the LLM section was updated in Jan 2024.
Limitations
- The paper states that GQA has no standard definition or categorization of hallucination and no automatic metric specifically for hallucination in GQA; it also notes that open-domain dialogue lacks a standard hallucination metric and that VL hallucination research is still in its early stage.
- The paper states that extrinsic hallucination has been somewhat overlooked and is more challenging to reduce, and that most existing mitigation methods do not distinguish between intrinsic and extrinsic hallucination.
- Evident from the text: as a survey, it does not provide new empirical validation of metrics or mitigation methods, and its LLM coverage is explicitly updated only through Jan 2024, so later work is not included.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
124 Valid · 26 Not valid · 19 Not checked · 135 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Furthermore, perturbation, where the insertions of most common tokens are placed at the beginning of the sentence, seems to be the most successful in hallucination mitigation.”
What the sources say
- Not checked — no full text of the sourcecites [133] [133] Katherine Lee, Orhan Firat, Ashish Agarwal, Clara Fannjiang, and David Sussillo. 2019. Hallucinations in Neural Machine Translation. ICLR (2019). -
- Disputedcites [215] [215] Vikas Raunak, Arul Menezes, and Marcin Junczys-Dowmunt. 2021. The Curious Case of Hallucinations in Neural Machine Translation. (4 2021), 1172-1183. https://arxiv.org/abs/2104.06683v1 - sourceExperimental — accuracy not yet measured
In the passage describing the perturbation procedure (page unavailable), the paper says that inserting common tokens at the beginning is used to generate hallucinations, not mitigate them. Its prevention section instead discusses approaches such as robust learning and corpus-level filtering. (LLM, conf=0.92)
Checked by a reasoning model — may be wrong.
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“While there are works on the visual extension of faithfulness-oriented RLHF [303], these essentially involve labeling more data, which is expensive and difficult to scale.”
What the sources say
- Disputedcites [303] [303] Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, and Tat-Seng Chua. 2023. RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback. CoRR abs/2312.00849 (2023). https://doi.org/10.48550/ARXIV.2312.00849 arXiv:2312.00849 - sourceExperimental — accuracy not yet measured
RLHF-V does use human annotation for visual-model alignment, but it makes the contrary point about needing more labeled data. The Fine-grained Correctional Human Preference Collection section says its corrections improve data efficiency, and Section 4.3 reports comparable hallucination rates using only 200 preference examples versus an order of magnitude more ranking-labeled examples. Our copy does not establish a separate claim about annotation cost or scalability. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
Every source the paper cites for this claim was checked and supports it.
In the paper
“Nevertheless, as illustrated by Falke et al. [66], off-the-shelf NLI models tend to transfer poorly to the abstractive summarization task.”
What the sources say
- Supportedcites [66] [66] Tobias Falke, Leonardo FR Ribeiro, Prasetya Ajie Utama, Ido Dagan, and Iryna Gurevych. 2019. Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . 2214-2220. - source
The Introduction states that models trained on NLI datasets transfer poorly to the paper’s downstream task of ranking generated summaries by correctness. The Conclusions likewise say that out-of-the-box NLI models do not perform well on that task. (LLM, conf=0.94)
- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Such wrong association results in generation with facts mixed up between two similar entities [60, 233].”
What the sources say
- Partly supportedcites [60] [60] Nouha Dziri, Andrea Madotto, Osmar Zaiane, and Avishek Joey Bose. 2021. Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding. EMNLP (2021). - sourceExperimental — accuracy not yet measured
The GPT2-KG passage describes an incorrect association between entities, and G Error Analysis gives an example of a generated response assigning a book to the wrong author. These support the claim that facts can be mixed up, but the paper does not say the entities involved are similar. The supplied passages do not provide page numbers. (LLM, conf=0.83)
- Supportedcites [233] [233] Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. 2021. Retrieval Augmentation Reduces Hallucination in Conversation. EMNLP (2021). - source
The Introduction states that language models often mix up facts between two similar entities when generating factually incorrect statements. This directly supports the cited description of the resulting error. (LLM, conf=0.92)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“As a result, the target reference may contain information that cannot be supported by the source [198, 268].”
What the sources say
- Supportedcites [198] [198] Ankur Parikh, Xuezhi Wang, Sebastian Gehrmann, Manaal Faruqui, Bhuwan Dhingra, Diyi Yang, and Dipanjan Das. 2020. ToTTo: A Controlled Table-To-Text Generation Dataset. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) . 1173-1186. - source
The Dataset section says that reference targets selected from web sentences may contain information that cannot be inferred from the source. The Data Annotation Process section also describes deleting phrases unsupported by table cells. (LLM, conf=0.93)
- Supportedcites [268] [268] Hongmin Wang. 2019. Revisiting Challenges in Data-to-Text Generation with Fact Grounding. In Proceedings of the 12th International Conference on Natural Language Generation . 311-322. - source
The Introduction reports that about 40% of human-written game-summary content cannot be directly mapped to the input boxscore records and draws on information beyond those inputs. Section 2.1 likewise describes reference content not licensed by the boxscore table. This supports the claim that a target reference may contain information the source does not support. (LLM, conf=0.93)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
117 more claims · 74 with their cited sources checked
Create a free account to see all 304 claims and to verify the 2 references still open.
- Borderline: one of the tests for a substantial claim is unclear. 1
- It may state two separate claims as one. 90
- Probably not a substantial claim. 142
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Hallucination can lead to serious consequences such as incorrect or misleading code, security risks, and ethical issues [186].”
From A survey on large language model based autonomous agents (2024) · cites this paper as [186]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“citation fabrication constitutes a form of extrinsic hallucination in the absence of retrieval augmentation, since the model generates references not grounded in any provided source material [4].”
From How LLMs Cite and Why It Matters: A Cross-Model Audit of Reference Fabrication in AI-Assisted Academic Writing and Methods to Detect Phantom Citations (2026) · cites this paper as [4]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Recent taxonomic work distinguishes at least seven cases [15,18].”
From Hallucination as epistemic pollution: epistemic injustice and credibility in futures-oriented science education (2026) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“LLMs struggle to generate accurate and up-to-date responses on current topics, due to outdated knowledge, lack of domain-specific expertise, or hallucination13–17.”
From Leveraging long context in retrieval augmented language models for medical question answering (2025) · cites this paper as [16]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Fine-tuning can enrich LLMs with domain knowledge, enhance their specific ability, improve the fairness and reliability of the outputs, and prevent certain damage caused by hallucination [26].”
From FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning (2024) · cites this paper as [26]
Experimental — accuracy not yet measured
41 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Extrinsic Object Hallucination
“CHAIR (Caption Hallucination Assessment with Image Relevance) metric, which calculates what proportion of object words generated are actually in the image according to the ground truth captions.”
§ Extrinsic Object Hallucination
“CHAIR 𝑖 measures per-instance object hallucination, i.e. what fraction of object instances in each generated caption are hallucinated.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 7.1 Hallucination Definition in Abstractive Summarization
“For instance, in Table 1, given the input article shown in the caption, an example of intrinsic hallucination is ' The Ebola vaccine was rejected by the FDA in 2019, '”
§ 2.1 Categorization
“in the abstractive summarization task from Table 1, the generated summary ' The first Ebola vaccine was approved in 2021 ' contradicts the source content”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Survey of Hallucination in Natural Language Generation
“The survey is organized into two parts: (1) a general overview of metrics, mitigation methods, and future directions; (2) an overview of task-specific research progress on hallucinations in the following downstream tasks, namely abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, and visual-language generation; and (3) hallucinations in large language models (LLMs)”
§ 1 INTRODUCTION
“The third part discusses this phenomenon in LLMs in Section 13.”
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 3×
“Recently, the rapid development of NLG has captured the imagination of many thanks to the advances in deep learning technologies, especially Transformer [189]-based models like BERT [29], BART [100], GPT-2 [149], and GPT-3 [16].”
BackgroundAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · cited 1×
“This work investigates the performances of GPT-3 [13], GPT-Neo/J [141], GPT-2 [105] and a T5-based model [106].”
BackgroundAdvances in Neural Information Processing Systems 14: Proceedings of the 2001 Conference
(2002) · The MIT Press eBooks · doi:10.7551/mitpress/1120.001.0001 · Cited by 8,890
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821 · cited 1×
“Recently, the development of NLG has conquered the imagination of many thanks to the advances in deep learning technologies, especially the Transformer [159]-based models like BERT [24], BART [83], GPT-2 [127], and GPT3 [13].”
BackgroundLewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816 · cited 1×
“Recently, the development of NLG has conquered the imagination of many thanks to the advances in deep learning technologies, especially the Transformer [159]-based models like BERT [24], BART [83], GPT-2 [127], and GPT3 [13].”
Background
Research works printed but not linked: 16
- [4] Joshua Albrecht and Rebecca Hwa. 2007. A Re-examination of Machine Learning Approaches for Sentence-Level MT Evaluation. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics . Association for Computational Linguistics, Prague, Czech Republic, 880-887. https://aclanthology.org/P07-1111 -
- [16] Andrzej Białecki, Robert Muir, Grant Ingersoll, and Lucid Imagination. 2012. Apache lucene 4. In SIGIR 2012 workshop on open source information retrieval . 17. -
- [53] Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. 2023. Improving Factuality and Reasoning in Language Models through Multiagent Debate. In Forty-first International Conference on Machine Learning . -
- [121] Philipp Koehn and Rebecca Knowles. 2017. Six Challenges for Neural Machine Translation. In First Workshop on Neural Machine Translation . Association for Computational Linguistics, 28-39. -
- [145] Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML . -
- [149] Tian Li, Ahmad Beirami, Maziar Sanjabi, and Virginia Smith. 2020. Tilted Empirical Risk Minimization. In International Conference on Learning Representations . -
- [164] Jiasen Lu, Jianwei Yang, Dhruv Batra, and Devi Parikh. 2018. Neural Baby Talk. In CVPR . -
- [165] Yukun Ma, Khanh Linh Nguyen, Frank Z Xing, and Erik Cambria. 2020. A Survey on Empathetic Dialogue Systems. Information Fusion 64 (2020), 50-70. -
- [175] Marianna J. Martindale, Marine Carpuat, Kevin Duh, and Paul McNamee. 2019. Identifying Fluently Inadequate Output in Neural and Statistical Machine Translation. In MTSummit . -
- [179] Kathleen McKeown. 1992. Text Generation . Cambridge University Press. -
- [209] Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. OpenAI Blog 1, 8 (2019), 9. -
- [238] Hui Su, Xiaoyu Shen, Sanqiang Zhao, Zhou Xiao, Pengwei Hu, Cheng Niu, and Jie Zhou. 2020. Diversifying Dialogue Generation with Non-Conversational Text. In 58th Annual Meeting of the Association for Computational Linguistics . ACL, 7087-7097. -
- [256] Zhaopeng Tu, Yang Liu, Lifeng Shang, Xiaohua Liu, and Hang Li. 2017. Neural Machine Translation with Reconstruction. In Thirty-First AAAI Conference on Artificial Intelligence . -
- [261] Neeraj Varshney, Wenlin Yao, Hongming Zhang, Jianshu Chen, and Dong Yu. 2023. A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation. CoRR abs/2307.03987 (2023). https://doi.org/10.48550/arXiv.2307.03987 arXiv:2307.03987 - · arXiv · doi:10.48550/arxiv.2307.03987 · Paper page
- [285] Zeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang, Xiang Gao, Chris Quirk, Rik Koncel-Kedziorski, Jianfeng Gao, Hannaneh Hajishirzi, Mari Ostendorf, et al. 2021. A Controllable Model of Grounded Response Generation. In Proceedings of the AAAI Conference on Artificial Intelligence , Vol. 35. 14085-14093. -
- [291] Xinnuo Xu, Ondřej Dušek, Verena Rieser, and Ioannis Konstas. 2021. AGGGEN: Ordering and Aggregating while Generating. roceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL2021) (2021). -
Cited by
Items 1,201–1,300 of 4,844
Design Patterns for Large Language Model Based Neuro-Symbolic Systems
de Boer, M., Smit, Q. T. S., van Bekkum, M. A., Meyer-Vitali, A., & Schmid, T. (2025) · Neurosymbolic Artificial Intelligence · doi:10.1177/29498732251377499 · Cited by 18
“…al., 2020) and inference (Samsi et al., 2023), but also the infamous phenomenon of hallucination: Situations where a trained LLM generates outputs presented as plausible or authoritative information that are factually incorrect, nonsensical, or unfaithful to the input or context (Ji et al., 2023).”
Kim, H., & Lee, S. W. (2025) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2025.102996 · Cited by 20
AI Hallucinations in Tourism: How Errors Impact Consumer Trust and Recommendation Acceptance
Rejón‐Guardia, F., Molinillo, S., & Anaya‐Sánchez, R. (2026) · Journal of Consumer Behaviour · doi:10.1002/cb.70105 · Cited by 17
El‐Ashry, A. M., Hermis, A. H., AL-Salih, S. S. H., Al-Jabri, M. M., Karim, N. A. H. A., Mohamed, H. A. A., Alkubati, S. A., AlOtaibi, N. G., Wahab, M. J., Hassan, A. A.-H., et al. (2026) · Nurse Education Today · doi:10.1016/j.nedt.2026.107011 · Cited by 8
Sapru, A. (2026) · Technology in Society · doi:10.1016/j.techsoc.2026.103251 · Cited by 12
Xie, W., Liu, F., Liu, J., & Liu, S. (2026) · Nurse Education Today · doi:10.1016/j.nedt.2026.107108 · Cited by 19
The diffusion of large language models in published academic articles
Siler, K. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2605754123 · Cited by 28
Sem Referências: o ChatGPT sob a perspectiva latouriana e a armadilha do Duplo Clique
Catalano, J. V. R., & Lorenzi, B. R. (2023) · Revista Faz Ciência · doi:10.48075/rfc.v25i41.30761 · Cited by 21
The Latest in Natural Language Generation: Trends, Tools and Applications in Industry
Skrodelis, H. K., Romānovs, A., Zeņina, N., & Gorskis, H. (2023) · IEEE Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE) · doi:10.1109/aieee58915.2023.10134841 · Cited by 15
“For example, in the medical field, a hallucinatory summary of patient information could endanger the patient and a life-threatening situation could arise if the instructions for medication generated by MT are hallucinatory [11].”
BackgroundTasks, Copilots, and the Future of Search: A Keynote at SIGIR 2023
White, R. W. (2023) · ACM SIGIR Forum · doi:10.1145/3642979.3642985 · Cited by 14
“This includes the tendency of generative AI to hallucinate (generate incorrect or non-sensical responses), be affected by biases [Liang et al., 2021; Ji et al., 2023], and affect searchers’ own biases [Leffer, 2023]; Learning: The impacts that the copilots can have on searchers, especially on their…”
BackgroundHistory Matters: Temporal Knowledge Editing in Large Language Model
Yin, X., Jin, J., Yang, L., & Wan, X. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29912 · Cited by 47
An Autoethnographic Reflection of Prompting a Custom GPT Based on Oneself
Lo, P. (2024) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3613905.3651096 · Cited by 12
Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation
Zhang, R., Ouni, J., & Eger, S. (2024) · Computational Linguistics · doi:10.1162/coli_a_00519 · Cited by 23
“However, despite the overall outstanding performance of ChatGPT summarization according to both humans, ChatGPT evaluation and automatic evaluation metrics, ChatGPT as a summarizer can also be prone to hallucination like other NLG systems (Bang et al. 2023; Ji et al. 2023).”
BackgroundEnhancing Large Language Models Through External Domain Knowledge
Welz, L., & Lanquillon, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-60615-1_9 · Cited by 17
de Arriba-Pérez, F., & García-Méndez, S. (2025) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-024-09508-2 · Cited by 8
“Unfortunately, despite the significant advancement they represent, llm s still exhibit certain limitations in open-domain task-oriented dialogues ( e.g. , medical use cases) [41].”
Geneş, M., & Çelik, M. (2024) · Life · doi:10.3390/life14101235 · Cited by 11
ChatGPT Provides References That Are Real, Inappropriate, or (Most Often) Fake
Hoffer, E. K. (2023) · Journal of Vascular and Interventional Radiology · doi:10.1016/j.jvir.2023.07.001 · Cited by 11
Towards Few-Shot Identification of Morality Frames using In-Context Learning
Roy, S., Nakshatri, N. S., & Goldwasser, D. (2022) · Workshop on Natural Language Processing and Computational Social Science (NLP+CSS) · doi:10.18653/v1/2022.nlpcss-1.20 · Cited by 25
A First Approach to the Generation of Linguistic Summaries from Glucose Sensors Using GPT-4
Martínez-Cruz, C., Guerrero, J., Ruiz, J. L. L., Rueda, A. J., & Espinilla, M. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-48642-5_4 · Cited by 9
ChatGPT Hallucinates Nonexistent Citations: Evidence from Economics
Buchanan, J., Hill, S., & Shapoval, O. (2023) · doi:10.2139/ssrn.4632842 · Cited by 8
Ma, S., Chen, Q., Wang, X., Zheng, C., Peng, Z., Yin, M., & Ma, X. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4772689 · Cited by 8
Nguyen, Q., Nguyen, D.-A., Dang, K., Liu, S., Nguyen, K., Wang, S. Y., Woof, W. A., Thomas, P. B. M., Patel, P. J., Balaskas, K., et al. (2024) · medRxiv · doi:10.1101/2024.11.18.24317510 · Cited by 11
LLM-augmented multi-agent cooperative framework for medical case retrieval in cardiology
Deng, L., Hu, H., Lu, K., & He, P. (2025) · Journal of King Saud University Computer and Information Sciences · doi:10.1007/s44443-025-00311-z · Cited by 8
“, LLMs struggle because their knowledge is frozen at training time and may be incomplete or outdated (Ji et al. 2023).”
InfluentialCalibrated Language Models Must Hallucinate
Kalai, A. T., & Vempala, S. S. (2023) · arXiv · Cited by 90
SciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation
Kasanishi, T., Isonuma, M., Mori, J., & Sakata, I. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.418 · Cited by 39
Workshop On Large Language Models' Interpretability and Trustworthiness (LLMIT)
Saha, T., Ganguly, D., Saha, S., & Mitra, P. (2023) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3583780.3615311 · Cited by 11
Lieder, F. R., & Schäffer, B. (2023) · Journal für Psychologie · doi:10.30820/0942-2285-2023-2-131 · Cited by 12
Intersectional Stereotypes in Large Language Models: Dataset and Analysis
Ma, W., Chiang, B., Wu, T., Wang, L., & Vosoughi, S. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.575 · Cited by 43
Hájek, A., & Horák, A. (2024) · IEEE Access · doi:10.1109/access.2024.3371689 · Cited by 10
Evaluating Intelligence and Knowledge in Large Language Models
Bianchini, F. (2024) · Topoi · doi:10.1007/s11245-024-10072-5 · Cited by 13
“LLMs are susceptible to “hallucinations” (Ji et al. 2023), meaning they can produce outputs that seem plausible but are disconnected from reality, potentially leading to the creation of misleading texts, fake news, and misinformation.”
Artificial intelligence in urology: a technology with transformative potential
Ananthapadmanabhan, S., Wang, H., Shanmugasundaram, R., Khadra, M. H., & Thangasamy, I. (2024) · Trends in Urology & Men s Health · doi:10.1002/tre.980 · Cited by 8
Barman, D., & Conlan, O. (2024) · ACM Conference on Hypertext and Social Media (HT) · doi:10.1145/3648188.3675125 · Cited by 14
The Factuality of Large Language Models in the Legal Domain
Hamdani, R. E., Bonald, T., Malliaros, F. D., Holzenberger, N., & Suchanek, F. M. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679961 · Cited by 25
Maximizing discrimination masking for faithful question answering with machine reading
Dong, L., Tang, J., Wang, P., Li, S., & Wang, T. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2024.103915 · Cited by 9
Knowledge Graphs for Enhancing Large Language Models in Entity Disambiguation
Pons, G., Bilalli, B., & Queralt, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-77844-5_9 · Cited by 21
“However, these LLMs still face some challenges, such as hallucination (i.e., the generation of statements that are factually incorrect) [20], and the lack of knowledge about concepts outside their training corpus.”
AI-Powered Neurogenetics: Supporting Patient’s Evaluation with Chatbot
Zampatti, S., Farro, J., Peconi, C., Cascella, R., Strafella, C., Calvino, G., Megalizzi, D., Trastulli, G., Caltagirone, C., & Giardina, E. (2024) · Genes · doi:10.3390/genes16010029 · Cited by 9
“It is well known that AI chatbots can provide hallucinations, including in their responses to wrong information or data that seems realistic [39,40].”
CBCMS: A Compliance Management System for Cross-Border Data Transfer
Zhuang, Z., Lee, X., Wei, J., Fu, Y., & Zhang, A. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10826075 · Cited by 14
“Moreover, LLMs can produce hallucinations and inconsistent predictions [32], making them less reliable for compliance management.”
Lee, J., & Lee, G. G. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113091 · Cited by 11
Karataş, Ö., Demirci, S., Pota, K., & Tuna, S. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14051747 · Cited by 8
“Therefore, future AI models should incorporate mechanisms to minimize misinformation and improve contextual adaptation to diverse populations and dietary habits [26,27].”
Kuan, C.-Y., & Lee, H.-Y. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888384 · Cited by 51
Zan, H., Javed, A., Abdullah, M. A. K., Rashid, J., & Faheem, M. R. (2025) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70004 · Cited by 10
Santiago, J. M., Sendner, M., Ralser, D., & Meschtscherjakov, A. (2025) · Applied Sciences · doi:10.3390/app15105506 · Cited by 12
Young, R., Matthews, A. M., & Poston, B. (2025) · Algorithms · doi:10.3390/a18050296 · Cited by 11
HSF: Defending against Jailbreak Attacks with Hidden State Filtering
Qian, C., Zhang, H., Sha, L., & Zheng, Z. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3701716.3717659 · Cited by 45
Lee, H., Kim, M., Baek, S., Zhou, W., Debbah, M. A., & Lee, I. (2025) · IEEE Communications Magazine · doi:10.1109/mcom.001.2400577 · Cited by 19
“In practice, this leads to fundamental challenges, such as the hallucination issue [8], which notably impairs the inference performance of LLMs [9].”
Visualizationary: Automating Design Feedback for Visualization Designers Using Large Language Models
Shin, S., Hong, S., & Elmqvist, N. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3579700 · Cited by 30
“Hallucination: Despite their capabilities, LLMs may produce nonsensical or unfaithful content, commonly referred to as hallucinations [31].”
Explainable AI for education: Enhancing essay scoring via rubric-aligned chain-of-thought prompting
Xu, W., Kassim, M. S. S., Hoo, W. L., Yang, W., & Xu, T. (2025) · International Journal of Modern Physics C · doi:10.1142/s0129183125420136 · Cited by 11
Engelstein, H., Ramon‐Gonen, R., Sabbag, A., Klang, E., Sudri, K., Cohen, M. S., & Barbash, I. M. (2025) · JMIR AI · doi:10.2196/74426 · Cited by 9
“This is especially important given the risk of hallucinations and overconfident misclassifications that LLMs may produce when faced with ambiguous or unfamiliar inputs [38].”
Zhang, Y. J., Zhang, Y., Wang, Y., Chen, T., & Yin, H. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730098 · Cited by 16
GINGER: Grounded Information Nugget-Based Generation of Responses
Łajewska, W., & Balog, K. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3730166 · Cited by 27
Sentiment-aware cross-modal semantic interaction model for harmful meme detection
Duan, Y., Zhao, X. H., & Guo, H. (2025) · Decision Support Systems · doi:10.1016/j.dss.2025.114509 · Cited by 12
Generative Artificial Intelligence With Youth Codesign to Create Vaping Awareness Advertisements
Leung, J., Sun, T., Stjepanović, D., Vu, G. T., Mekonen, T., Connor, J. P., Hall, W., & Chan, G. (2025) · JAMA Network Open · doi:10.1001/jamanetworkopen.2025.14040 · Cited by 11
Human-guided collective LLM intelligence for strategic planning via two-stage information retrieval
Kim, S., Ha, J., Lee, H., Park, S., & Cho, S. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104288 · Cited by 17
An empirical study of LLMs via in-context learning for stance classification
Shi, L., Giunchiglia, F., Luo, R., Shi, D., Song, R., Diao, X., & Xu, H. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104322 · Cited by 12
A knowledge-graph-based pharmaceutical engineering chatbot for drug discovery
Taskiran, N. P., Tsai, C.-E. J., Huang, S., Chakraborty, A., & Venkatasubramanian, V. (2025) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2025.109318 · Cited by 14
IRAGKR:Iterative retrieval augmented generation with fine-grained knowledge refinement
Du, K., Wang, W., Zhang, B., Wang, P., Zhang, F., Lin, C., & Guo, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131282 · Cited by 15
Evaluation of cell type annotation reliability using a large language model-based identifier
Ye, W., Ma, Y., Xiang, J., Liang, H., Luo, J., Li, Y., Wang, T., Xiang, Q., Song, W., Li, W., et al. (2025) · Communications Biology · doi:10.1038/s42003-025-08745-x · Cited by 15
Hao, H., Si, G., Lu, L., Liu, Q., & Zhou, F. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131590 · Cited by 11
The AI Annotator: Large Language Models’ Potential in Scoring Sustainability Reports
Wu, Y., Hu, P., & Wang, D. D. (2025) · Systems · doi:10.3390/systems13100899 · Cited by 13
“Despite the impressive capabilities of LLMs trained on large text corpora, recent studies indicate that LLMs are prone to hallucinations in various applications [71,72].”
Wang, Y., & Guo, R. (2025) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2025.104588 · Cited by 14
Understanding Human-AI Misalignment in LLM-Based Job-Seeking Support for Neurodivergent Users
Hall, K., Ma, M., Zhang, X., Swain, V. D., & Kim, J. G. (2025) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663547.3746361 · Cited by 10
Zhou, Y., & Chen, Y. (2025) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-025-00353-3 · Cited by 19
INKER: Adaptive dynamic retrieval augmented generation with internal-external knowledge integration
Zhou, M., Tang, J., Zeng, W., & Zhao, X. (2025) · Information Processing & Management · doi:10.1016/j.ipm.2025.104534 · Cited by 9
Hallucination-Aware Optimization for Large Language Model-Empowered Communications
Liu, Y., Liu, G., Zhang, R., Niyato, D. T., Xiong, Z., Kim, D. I., Huang, K., & Du, H. (2026) · IEEE Communications Magazine · doi:10.1109/mcom.001.2400688 · Cited by 27
“Specifically, model-based strategies leverage NLP techniques, represented by hallucination detection dataset, RAG, and prompt engineering, to improve the performance of individual LLMs [4, 5].”
InfluentialMachine Learning for Catalytic Reaction Systems: A Framework for Complex Chemical Processes
Günay, M. E., & Yıldırım, R. (2026) · ACS Engineering Au · doi:10.1021/acsengineeringau.5c00093 · Cited by 15
Human-AI Collaboration: Balancing Trust, Emotion, and Productivity
Khullar, S., Baghel, R. S., & Swami, P. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-7534-2.ch003 · Cited by 7
LLM-based multi-agent system for dam structural health monitoring
Liu, C., Qu, R., Liu, C., Wang, J., & Pan, J. (2026) · Automation in Construction · doi:10.1016/j.autcon.2026.106895 · Cited by 11
Mitigating hallucinations in healthcare AI: a systematic review of evidence-based strategies
Basu, S., & Huynh, B. Q. (2026) · BMC Health Services Research · doi:10.1186/s12913-026-14851-1 · Cited by 18
“[10] In healthcare AI specifically, hallucinations may manifest as fabricated clinical guidelines, invented medical literature citations, misrepresented diagnostic criteria, inaccurate patient records, or incorrect treatment protocols.”
MultiQG-TI: Towards Question Generation from Multi-modal Sources
Wang, Z., & Baraniuk, R. G. (2023) · Workshop on Innovative Use of NLP for Building Educational Applications · doi:10.18653/v1/2023.bea-1.55 · Cited by 17
Generating Factually Consistent Sport Highlights Narrations
Sarfati, N., Yerushalmy, I., Chertok, M., & Keller, Y. (2023) · ACM International Workshop on Multimedia Content Analysis in Sports (MMSports) · doi:10.1145/3606038.3616157 · Cited by 12
Generative Models for Product Attribute Extraction
Blume, A., Zalmout, N., Ji, H., & Li, X. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-industry.55 · Cited by 30
SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation
Clark, E., Rijhwani, S., Gehrmann, S., Maynez, J., Aharoni, R., Nikolaev, V. A., Sellam, T., Siddhant, A., Das, D., & Parikh, A. P. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.584 · Cited by 62
Explain-and-Test: An Interactive Machine Learning Framework for Exploring Text Embeddings
Raval, S., Wang, C., Viégas, F. B., & WATTENBERG, M. P. (2023) · Visualization · doi:10.1109/vis54172.2023.00052 · Cited by 9
“Of course, language-model-based AI can famously produce “halluci-nations” [12, 15]: reasonable-seeming results that turn out to be confabulated.”
BackgroundTrICy: Trigger-Guided Data-to-Text Generation With Intent Aware Attention-Copy
Agarwal, V., Ghosh, S. K., Harichandana, B. S. S., Arora, H., & Raja, B. R. K. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3353574 · Cited by 10
“Data-to-text generation is particularly prone to this [60].”
BackgroundChat GPT-4: Potentials, barriers, and future directions for newer medical researchers
Garg, S., & Chauhan, A. (2024) · The American Journal of the Medical Sciences · doi:10.1016/j.amjms.2024.03.016 · Cited by 7
Marey, A., Serdysnki, K. C., Killeen, B. D., Unberath, M., & Umair, M. (2024) · BJR|Artificial Intelligence · doi:10.1093/bjrai/ubae008 · Cited by 7
“102,103 Regulation and accountability for fair and accountable AI To cultivate fair and accountable AI practices within health-care, a regulatory framework becomes essential.”
Kim, H. K., Roknaldin, A., Nayak, S., Zhang, X., Twyman, M. D., Hwang, A. H., & Lu, S. C.-Y. (2024) · ASEE Pacific Southwest Section Conference (PSW) · doi:10.18260/1-2--46032 · Cited by 10
Using Large Language Models for Robot-Assisted Therapeutic Role-Play: Factuality is not enough!
Höhn, S., Nasir, J., Paikan, A., Ziafati, P., & André, E. (2024) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3640794.3665886 · Cited by 9
Towards Industrial Foundation Models: Framework, Key Issues and Potential Applications
Wang, Y., Yang, C., Lan, S., Fei, W., Wang, L., Huang, G. Q., & Zhu, L. (2024) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd61410.2024.10580089 · Cited by 13
Gitzel, R., Hoffmann, M. W., Heiden, P. Z., Skolik, A., Kaltenpoth, S., Müller, O., Kanak, C., Kandiah, K., Stroh, M.-F., Boos, W., et al. (2024) · IEEE Access · doi:10.1109/access.2024.3437195 · Cited by 15
“LLM hallucinations are factually incorrect or off-topic generations by LLMs [45].”
BackgroundA Hybrid Intelligence Method for Argument Mining
van der Meer, M., Liscio, E., Jonker, C. M., Plaat, A., Vossen, P. T. J. M., & Murukannaiah, P. K. (2024) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.15135 · Cited by 13
“However, having such LLMs reliably process large amounts of citizen feed-back without hallucinations is a nontrivial task, and the danger of models synthesizing ungrounded arguments exists (Ji et al., 2023).”
BackgroundToward Reliable Biodiversity Information Extraction From Large Language Models
Elliott, M. J., & Fortes, J. A. B. (2024) · IEEE International Conference on eScience · doi:10.1109/e-science62913.2024.10678666 · Cited by 13
“Additional uncertainty measures can also be imagined, such as quantifying the factual consistency of top-scoring documents, using natural language inference to determine the truth of a response according to retrieved documents [3], or measuring changes in text generations after applying RAG.”
BackgroundInfluentialAttacks and Defenses for Large Language Models on Coding Tasks
Zhang, C., Wang, Z., Zhao, R., Mangal, R., Fredrikson, M., Jia, L., & Păsăreanu, C. S. (2024) · IEEE/ACM International Conference on Automated Software Engineering (ASE) · doi:10.1145/3691620.3695297 · Cited by 32
RD-P: A Trustworthy Retrieval-Augmented Prompter with Knowledge Graphs for LLMs
Huang, Y., & Zeng, G. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679659 · Cited by 15
Using Generative AI to Provide Feedback to Adult Tutors in Training and Assess Real-Life Performance
Thomas, D. R., Gatz, E., Gupta, S., Lin, J., Tipper, C., & Koedinger, K. R. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-73427-4_21 · Cited by 14
HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning
Wang, Z., Bingham, G., Yu, A. W., Le, Q. V., Luong, M.-T., & Ghiasi, G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72980-5_17 · Cited by 64
Cadena-Bautista, Á., Lopez-Ponce, F. F., Ojeda-Trueba, S.-L., Sierra, G., & Bel-Enguix, G. (2025) · Information · doi:10.3390/info16020077 · Cited by 9
Bhatnagar, M., & Huchhanavar, S. (2025) · Artificial Intelligence and Law · doi:10.1007/s10506-025-09441-1 · Cited by 8
Evaluating Large Language Models for Burning Mouth Syndrome Diagnosis
Suga, T., Uehara, O., Abiko, Y., & Toyofuku, A. (2025) · Journal of Pain Research · doi:10.2147/jpr.s509845 · Cited by 8
Dey, P., Merugu, S., & Kaveri, S. R. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3701716.3715523 · Cited by 25
Benchmarking Visual Language Models on Standardized Visualization Literacy Tests
Pandey, S., & Ottley, A. (2025) · Computer Graphics Forum · doi:10.1111/cgf.70137 · Cited by 38
“Furthermore, VLMs exhibit unique challenges, such as a tendency to hallucinate or produce unreliable outputs that are highly sensitive to prompt phrasing and order effects, calling into question their robustness in visualization tasks [JLF ∗ 23,LYT ∗ 23].”
Large Language Model assisted Transformation of Software Variants into a Software Product Line
Stümpfle, J., Atray, D., Jazdi, N., & Weyrich, M. (2025) · International Conference on Software Reuse · doi:10.1109/icsr66718.2025.00008 · Cited by 16
“The phenomenon of hallu-cination occurs when the model generates outputs that are confidently presented but are factually incorrect or nonsensical [31].”
Jiang, X., Dong, Y., Tao, Y., Liu, H., Jin, Z. G., & Li, G. (2025) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1109/icse55347.2025.00133 · Cited by 42
The Web Can Be Your Oyster for Improving Language Models
Li, J., Tang, T., Zhao, W. X., Wang, J., Nie, J., & Wen, J.-R. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.46 · Cited by 20
PapagAI: Automated Feedback for Reflective Essays
Solopova, V., Rostom, E., Cremer, F., Gruszczynski, A., Witte, S., Zhang, C., López, F. R., Plößl, L., Hofmann, F., Romeike, R., et al. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-42608-7_16 · Cited by 17
An AI Chatbot for Explaining Deep Reinforcement Learning Decisions of Service-Oriented Systems
Metzger, A., Bartel, J., & Laufer, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-48421-6_22 · Cited by 13
Expository Text Generation: Imitate, Retrieve, Paraphrase
Balepur, N., Huang, J., & Chang, K. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.729 · Cited by 4
Xue, B., Wang, W., Wang, H., Mi, F., Wang, R., Wang, Y., Shang, L., Jiang, X., Liu, Q., & Wong, K. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.525 · Cited by 28
Question Answering as Programming for Solving Time-Sensitive Questions
Zhu, X., Yang, C., Chen, B., Li, S., Lou, J., & Yang, Y. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.787 · Cited by 25
ChatGPT and Bard in Plastic Surgery: Hype or Hope?
Labouchère, A., & Raffoul, W. (2024) · Surgeries · doi:10.3390/surgeries5010006 · Cited by 9
“…that GAIs have completely made up answers and references (“neural hallucinations”), which underlines the fact that they are prone to errors (e.g., references, interpretation) and can miss, overlook or misinterpret information (e.g., relevant studies, medical nuances), let alone be biased [28,29].”
Background
Metadata
- Authors
- Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- ORCID
- Venue
- ACM Computing Surveys
- Published
- 2023-03-03
- Volume
- 55
- Issue
- 12
- Pages
- 1-38
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W4309674289
- Semantic Scholar
- 3def68bd0f856886d34272840a7f81588f2bc082
- Cited by
- 5,025
- References
- 111
- Citations by year
- 2026: 2296 · 2025: 1441 · 2024: 817 · 2023: 453
- FWCI
- 224.36
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Computing Surveys (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- hallucinations, natural language generation, hallucination mitigation, abstractive summarization, dialogue generation, generative question answering, data-to-text generation, machine translation, large language models, transformer models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-30 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.




